Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

InferIndex

REMOTE · MCP.INFERINDEX.DEV · SCANNED SEP 20

LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.

68 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security69
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1351 tokens (~270/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management7
  • Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the InferIndex MCP server?

InferIndex is a hosted endpoint at https://mcp.inferindex.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.inferindex.dev

# add to Claude Code
claude mcp add --transport http inferindex-inferindex 'https://mcp.inferindex.dev/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "inferindex-inferindex": {
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "inferindex-inferindex": {
      "type": "http",
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.inferindex-inferindex]
url = "https://mcp.inferindex.dev/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "inferindex-inferindex": {
      "type": "remote",
      "url": "https://mcp.inferindex.dev/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add inferindex-inferindex --url 'https://mcp.inferindex.dev/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  inferindex-inferindex:
    url: "https://mcp.inferindex.dev/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "inferindex-inferindex": {
      "Transport": "http",
      "Url": "https://mcp.inferindex.dev/mcp"
    }
  }
}
# add to Vellum
assistant mcp add inferindex-inferindex -t streamable-http -u 'https://mcp.inferindex.dev/mcp'
// mcp.json
{
  "mcpServers": {
    "inferindex-inferindex": {
      "type": "http",
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1
    • Stability: unverified → 0.03 functional
  • 18 Sept 26 67

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://mcp.inferindex.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=inferindex.dev CN=WE1,O=Google Trust Services,C=US 18 Sept 2026 17 Dec 2026 ECDSA 256 ECDSA-SHA256 4106ef29a92df59513cd213b8152ab7e
SANs: inferindex.dev, mcp.inferindex.dev, *.mcp.inferindex.dev
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.inferindex.dev. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
inferindex.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
content-security-policy default-src 'none'; frame-ancestors 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.inferindex.dev/mcp Verified 200
http (plaintext) http://mcp.inferindex.dev/mcp Inconclusive 405
MCP tools · 5 exposed · ~1,276 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
cheapest ~419

Cheapest current API offers for one model across direct providers and aggregators, in USD per 1M tokens (input, output, blended 3:1). Stale prices, and flex/batch tiers, are excluded by default. Optional filters (context, tools, JSON, vision, region, no training on prompts, open sign-up) and usage (tokens per request, requests per day) to get an estimated cost per request and per month. Returns the winner and the first offers.

NameTypeReqDescription
cached_rationumberShare of input tokens served from the provider's prompt cache (0 to 1)
include_tiersstringAlso include lower-priority service tiers, comma-separated: flex, batch (hidden by default)
jsonbooleanOnly offers that support JSON output
limitintegerNumber of offers to return (default 5, max 25)
min_contextintegerMinimum context window in tokens
modelstringyesModel id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure.
no_trainingbooleanOnly providers whose published terms say they do not train on your prompts
no_waitlistbooleanOnly providers with open sign-up (no waitlist or invitation)
output_tokensintegerOutput tokens per request, for the estimated cost
prompt_tokensintegerInput tokens per request, for the estimated cost
regionstringOnly providers that process data in this region: eu, us, …
requests_per_dayintegerRequests per day, to also get an estimated monthly cost
strictbooleanExclude offers whose provider does not publish the filtered information (by default they are kept and flagged)
toolsbooleanOnly offers that support tool calling
visionbooleanOnly offers that accept image input

No output schema declared.

No examples provided.

compare_providers ~345

Current offers for one model, one line per provider and source (direct or via an aggregator), cheapest first (10 by default), with price, context, quantization, published conditions (training on prompts, data regions, sign-up) and reliability from official status pages.

NameTypeReqDescription
cached_rationumberShare of input tokens served from the provider's prompt cache (0 to 1)
include_tiersstringAlso include lower-priority service tiers, comma-separated: flex, batch (hidden by default)
limitintegerNumber of offers to return (default 10, max 50)
modelstringyesModel id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure.
no_trainingbooleanOnly providers whose published terms say they do not train on your prompts
no_waitlistbooleanOnly providers with open sign-up (no waitlist or invitation)
output_tokensintegerOutput tokens per request, for the estimated cost
prompt_tokensintegerInput tokens per request, for the estimated cost
regionstringOnly providers that process data in this region: eu, us, …
requests_per_dayintegerRequests per day, to also get an estimated monthly cost
sortstringSort order (default blended); estimated_cost needs prompt_tokens or output_tokens
strictbooleanExclude offers whose provider does not publish the filtered information (by default they are kept and flagged)

No output schema declared.

No examples provided.

estimate_cost ~203

Estimated cost of a workload on one model at each provider: cost per request, and per month if requests_per_day is given, taking the provider's tiered pricing and prompt-cache price into account. Offers sorted by estimated cost, cheapest first.

NameTypeReqDescription
cached_rationumberShare of input tokens served from the provider's prompt cache (0 to 1)
limitintegerNumber of offers to return (default 5, max 25)
modelstringyesModel id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure.
output_tokensintegerOutput tokens per request, for the estimated cost
prompt_tokensintegerInput tokens per request, for the estimated cost
requests_per_dayintegerRequests per day, to also get an estimated monthly cost

No output schema declared.

No examples provided.

price_history ~240

Price history of one model: every offer tracked by InferIndex (daily or weekly min/max/last price in USD, or raw price changes), plus the official price of the model's lab over time. Give either days, or from/to (YYYY-MM-DD), or at (a date) for the prices in effect that day.

NameTypeReqDescription
atstringA single date, YYYY-MM-DD: prices in effect that day
daysintegerNumber of days back from today (default 7)
fromstringStart date, YYYY-MM-DD (with to, instead of days)
granularitystringday (default), week, or raw price changes
limitintegerMaximum number of points (default 100, max 500)
modelstringyesModel id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure.
providerstringOnly this provider
tostringEnd date, YYYY-MM-DD

No output schema declared.

No examples provided.

search_models ~69

Find the exact id of an LLM tracked by InferIndex from a name or partial name (e.g. 'deepseek', 'qwen3 max', 'claude opus'). Returns matching model ids and names, best match first.

NameTypeReqDescription
querystringyesModel name or part of it

No output schema declared.

No examples provided.

Common questions

What is the InferIndex MCP server?

InferIndex is an MCP server listed in the public MCP registry as io.github.InferIndex/inferindex. LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates. This page covers its hosted endpoint (https://mcp.inferindex.dev/mcp).

Is the InferIndex MCP server safe to use?

InferIndex scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the InferIndex MCP server expose?

InferIndex exposes 5 tools: search_models, cheapest, compare_providers, price_history, estimate_cost. Their descriptions and schemas cost roughly 1,276 tokens of context every time the server is loaded.

Does the InferIndex MCP server require authentication?

No. We connected to InferIndex without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the InferIndex MCP server still maintained?

InferIndex is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.